{"version":"1","model":{"id":"elevenlabs/speech-to-text/scribe-v2-realtime","name":"ElevenLabs Scribe v2 Realtime","kind":"audio","availability":"available","available":true,"restricted":false,"api_key_only":false,"description":"Transcribe an uploaded audio clip through ElevenLabs' real-time Scribe WebSocket model. Supports 90+ languages and vocabulary hints. ArtEmotion returns the completed transcript; this is not a live microphone session. Maximum clip length: 10 minutes.","pricing_note":"$0.39 / source hour; keyterms add $0.05 / hour.","categories":["transcribe"],"prompt_required":false,"prompt_supported":false,"supports":{"referenceAudio":true},"requires":{"referenceAudio":true},"aspect_ratios":[],"resolutions":[],"durations":[],"reference_audio_duration":{"min_seconds":2,"max_seconds":600},"max_input_bytes":{"audio":134217728},"base_credits":2,"api_gross_margin_percent":20,"added_at":"2025-11-11","popularity_rank":21,"preview":{"image":"/images/model-previews/generated/elevenlabs-scribe-v2-realtime-v1.webp"},"schema_url":"/api/v1/models?id=elevenlabs%2Fspeech-to-text%2Fscribe-v2-realtime","input_schema":{"$schema":"https://json-schema.org/draft/2020-12/schema","$id":"https://www.artemotion.ai/api/v1/models?id=elevenlabs%2Fspeech-to-text%2Fscribe-v2-realtime","title":"ElevenLabs Scribe v2 Realtime generation request","description":"Request body accepted by POST /api/v1/generate for elevenlabs/speech-to-text/scribe-v2-realtime.","type":"object","properties":{"model_id":{"type":"string","const":"elevenlabs/speech-to-text/scribe-v2-realtime","description":"ArtEmotion model identifier."},"extra":{"type":"object","additionalProperties":true,"description":"Model-specific settings may also be nested here."},"max_credits":{"type":"number","minimum":1,"description":"Reject before submission if the estimated list price exceeds this cap."},"webhook_url":{"type":"string","format":"uri","maxLength":2048},"webhook_secret":{"type":"string","maxLength":512},"folder_id":{"type":"string"},"language_code":{"title":"Language","description":"Optional ISO language code, such as en, es, eng, or spa. Leave empty to detect the language automatically.","default":"","type":"string","minLength":2,"maxLength":3},"keyterms":{"title":"Keyterms","description":"Vocabulary hints; each term is at most 5 words. Adds a surcharge to transcription, included by /api/v1/estimate.","type":"array","items":{"type":"string","minLength":1,"maxLength":50},"maxItems":1000},"audio_url":{"type":"string","format":"uri"},"duration":{"type":"number","minimum":2,"maximum":600,"default":60,"description":"Estimate-only fallback when no media is supplied. Generation measures source bytes before reserving credits; client duration cannot lower the bill."}},"required":["model_id","audio_url"],"additionalProperties":false},"parameters":[{"key":"language_code","label":"Language","type":"text","default":"","description":"Optional ISO language code, such as en, es, eng, or spa. Leave empty to detect the language automatically."},{"key":"keyterms","label":"Keyterms","type":"string_array","max_items":1000,"description":"Vocabulary to recognize accurately: up to 1,000 terms, each at most 50 characters and 5 words. Adds a transcription surcharge."}]}}